ActivePDF Releases DocSight OCR v4.1.0

LAGUNA NIGUEL, CA, Aug 14, 2018 – ActivePDF, the leading provider of PDF automation technologies and digital transformation solutions, recently announced the release of DocSight OCR 4.1.0, with the newly added Verifier component and zonal OCR data capture add-on functionalities. OCR 4.1.0 features full text Optical Character Recognition (OCR) capabilities, giving organizations the ability to search and extract critical data from scanned documents. Zonal extraction technology targets specified data such as names, dates, account numbers, phone numbers, and more.

The new DocSight Verifier works with OCR 4.1.0, enabling users to verify 100% of their automated data entry and data extraction from any browser. Once data is extracted, the Verifier component provides a suggestion of what the user should confirm if certain targeted fields do not match the set-confidence threshold level. Users then open the files and manually correct the suspect characters, or confirm that they are correct. OCR 4.1.0 is ideal for businesses that require high-volume document automation and data capture in areas such as Accounts Payable, Banking, Financial Services, Government, Healthcare, Legal, Manufacturing, Transportation, and Utilities.

OCR 4.1.0 features include:

  • DocSight Verifier: This critical component to OCR 4.1.0 is a browser-based application that verifies data extracted from scanned documents and provides a list of data to double check. Once these characters are identified, you can edit, change or correct them from any browser without the need for additional software.
  • Multiple Page Support: An enhanced feature to OCR 4.1.0, users may extract data spanning more than one page into a single row or record for .CSV output. For example, if capturing data from a multiple-page bill where the address data field starts on page 1 and carries over to page 2, OCR can recognize that the data on the second page belongs with the first page.
  • Zonal Data Capture: This OCR add-on enables users to specify areas for capture by defining zones on documents that contain important data for extraction. This could include invoices or documents with a customer’s name, address, account number, billing charges, form data, or contract information.
  •  .CSV Output: After capturing and extracting data, OCR 4.1.0 verifies the accuracy based on your confidence level settings and then outputs it to a .CSV file for import into your existing backend systems, avoiding manual data entry.
  •  Suspect Character Highlight: If OCR 4.1.0 finds suspect characters that do not meet the confidence level set by the administrator, conversion stops and is flagged for validation. This is where Verifier is crucial in the next steps of verifying and correcting suspect data.
  •  Configuration Manager Update: Support for multiple OCR profiles allows you to capture many different types of files and documents with watch folder technology for full automation or drag-and-drop operations.
  •  Template and Template Editor: Create a collection of file templates, defining the areas or zones to extract and verify data.

“OCR 4.1.0 is essential for enterprise businesses moving closer to complete digital transformation,” says Tim Sullivan, ActivePDF chief architect and CEO. “ActivePDF’s OCR solution without Verifier delivers the accuracy our customers need to process things such as invoices 80% faster, with 60% fewer people, and cut AP cost per invoice by 50% in three months. Additionally, because it’s browser based, OCR 4.1.0 is easy to use and deploy, delivering immediate satisfaction through automation, helping businesses save time, money, and manpower. I’m excited at what possibilities the future holds with digital transformation and OCR in combination with our .NET PDF tools.”

Request a DocSight OCR 4.1.0 demo. To learn more about DocSight Verifier, please click here.

About ActivePDF 

Developers, Product Managers, CIOs, and CTOs partner with ActivePDF to embed digital transformation and powerful PDF tools into their enterprise applications that reliably scale for millions of users. Originally known for providing low-code .NET PDF APIs that create, convert, modify, and view files, ActivePDF has naturally evolved over the years to further provide OCR data capture and intelligent workflow automation solutions within existing business processes. While represented amongst 40% of Fortune 500 companies, the full suite of ActivePDF technologies are currently deployed in industries such as banking, financial services, government, healthcare, legal, manufacturing, utilities, and more.

Explore everything PDF, visit

Leave a Reply

Your email address will not be published. Required fields are marked *